Adding Evaluation Results
#1
by
leaderboard-pr-bot
- opened
README.md
CHANGED
|
@@ -303,4 +303,17 @@ All airoboros models and datasets are intended and licensed for research use onl
|
|
| 303 |
- the base model is LLaMa, which has it's own special research license
|
| 304 |
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
|
| 305 |
|
| 306 |
-
So, to reiterate: this model (and datasets) cannot be used commercially.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 303 |
- the base model is LLaMa, which has it's own special research license
|
| 304 |
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
|
| 305 |
|
| 306 |
+
So, to reiterate: this model (and datasets) cannot be used commercially.
|
| 307 |
+
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
| 308 |
+
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_bhenrym14__airoboros-33b-gpt4-1.4.1-lxctx-PI-16384-fp16)
|
| 309 |
+
|
| 310 |
+
| Metric | Value |
|
| 311 |
+
|-----------------------|---------------------------|
|
| 312 |
+
| Avg. | 47.87 |
|
| 313 |
+
| ARC (25-shot) | 60.58 |
|
| 314 |
+
| HellaSwag (10-shot) | 82.97 |
|
| 315 |
+
| MMLU (5-shot) | 52.1 |
|
| 316 |
+
| TruthfulQA (0-shot) | 46.1 |
|
| 317 |
+
| Winogrande (5-shot) | 73.64 |
|
| 318 |
+
| GSM8K (5-shot) | 8.11 |
|
| 319 |
+
| DROP (3-shot) | 11.55 |
|